Real-time Hyperspectral Imaging for Non-invasive Monitoring of Tissue Ischemia

Abstract

This paper presents a study on the use of hyperspectral imaging (HSI) for non-invasive, real-time monitoring of skin ischemia. We propose a novel ischemia index based on reflectance in a limited number of wavelengths, which can be calculated and visualized in real-time with low memory requirements. The index is tested on hyperspectral images of healthy and ischemic forearms, obtained by performing lower arm occlusion, and is compared to five other state-of-the-art indices from literature using binary support vector machines (SVMs). The results show that the proposed index is able to robustly distinguish between healthy and ischemic tissue in real-time, thus highlighting their potential to be used in a clinical setting.